Mayo endoscopic subscores (MES) are used to identify disease activity in patients with UC. However, observer variance up to 75% has been reported. Dr Bobby Lo (Hvidovre Hospital, Denmark) and colleagues aimed to develop a deep learning model that is able to distinguish between the 4 MES scores [1].
Initially, 1,484 endoscopic images from 467 UC patients were scored independently by 2 experts. Subsequently, 85% of the images was used as a training set for the machine learning process. The other 15% was used as a test set. The developed deep learning model outperformed human evaluation of the endoscopic images, distinguishing between all MES scores with an accuracy of 84% for the test set, with a sensitivity of 88% and a specificity of 81%. In addition, the deep learning model demonstrated excellent results of distinguishing between inactive to mild (MES 0-1) and moderate to severe (MES 2-3) disease. On the other hand, the weighted kappa value between the 2 expert assessors was 0.66.
Dr Lo mentioned that the model is currently launched for local usage and that the model is under evaluation as a training tool for inexperienced physicians.
- Lo B, et al. Artificial intelligence surpasses gastrointestinal experts in the classification of endoscopic severity among Ulcerative Colitis. OP07, ECCO 2021 Virtual Congress, 2-3 & 8-10 July.
Copyright ©2021 Medicom Medical Publishers
Posted on
Previous Article
« Early clinical remission and response following risankizumab therapy in CD Next Article
Promising safety and pharmacokinetic data on BT051 for UC »
« Early clinical remission and response following risankizumab therapy in CD Next Article
Promising safety and pharmacokinetic data on BT051 for UC »
Table of Contents: ECCO 2021
Featured articles
Biologics Updates
Similar efficacy of ustekinumab and adalimumab for moderate-to-severe CD
Ustekinumab safe and effective in elderly CD patients
Early clinical remission and response following risankizumab therapy in CD
Risk of hospitalisation and surgery linked to IBD biological
Obesity increases the risk of immunogenicity to adalimumab in IBD
Improvements in Small Molecules
Upadacitinib meets primary endpoint for moderate-to-severe UC
Promising safety and pharmacokinetic data on BT051 for UC
Surgical closure plus anti-TNF outperforms anti-TNF alone for perianal fistula
Novel Biomarkers
Blood proteins predicting relapse in CD identified
Extracellular RNA has potential as a non-invasive biomarker in IBD
Risk Mitigation
No increased risk of (severe) COVID-19 among IBD patients
Oral faecal microbiota transplant therapy efficacious in UC
Artificial intelligence outperforms human classifying of endoscopic images in UC
Increased risk of rectal cancer after colectomy in IBD
Risk of colorectal cancer is detected by low-pass whole genome sequencing
Large variability in IBD care and education across Europe
Ultra-processed food intake associated with IBD
Factors of coping difficulties in IBD revealed
Related Articles
April 14, 2020
Pipeline of IBD drugs
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy